Correction of the NSE concentration in hemolyzed serum samples improves its diagnostic accuracy in small-cell lung cancer

Abstract

Neuron-specific enolase (NSE) is a well-known biomarker for the diagnosis, prognosis and treatment monitoring of small-cell lung cancer (SCLC). Nevertheless, its clinical applicability is limited since serum NSE levels are influenced by hemolysis, leading to falsely elevated results. Therefore, this study aimed to develop a hemolysis correction equation and evaluate its role in SCLC diagnostics. Two serum pools were spiked with increasing amounts of hemolysate obtained from multiple individuals. A hemolysis correction equation was obtained by analyzing the relationship between the measured NSE concentration and the degree of hemolysis. The equation was validated using intentionally hemolyzed serum samples, which showed that the correction was accurate for samples with an H-index up to 30 μmol/L. Correction of the measured NSE concentration in patients suspected of lung cancer caused an increase in AUC and a significantly lower cut-off value for SCLC detection when compared to uncorrected results. Therefore, a hemolysis correction equation should be used to correct falsely elevated NSE concentrations. Results of samples with an H-index above 30 μmol/L should not be reported to clinicians. Application of the equation illustrates the importance of hemolysis correction in SCLC diagnostics and questions the correctness of the currently used diagnostic cut-off value.

Keywords: hemolysis correction equation; neuron-specific enolase; protein tumor markers; small-cell lung cancer.

Figure 1. The influence of hemolysis on the measured NSE concentration.

(A) A hemolysate spiking study showing a hemolysis-dependent elevation of measured NSE concentration in two serum pools spiked with increasing amounts of hemolysate derived from five individuals (a–e). (B) Derivation of the hemolysis correction equation by combining all pools and plotting the corresponding ΔNSE concentration as a function of H-index.

Figure 2. Validation of the hemolysis correction equation.

(A) The difference between corrected and baseline NSE values of all hemolysate pools (a-j) spiked in serum pool 1 and 2 plotted as a function of H-index. The dashed lines indicate the mean ± 2SD, the dotted line illustrates the H-index level at which the mean ± 2SD equalizes 2TEa (H-index = 30). (B) Boxplots of the differences between (un) corrected and baseline NSE values, showing a significant difference between uncorrected and corrected values. (C) QQ-plots of the difference between baseline, uncorrected and corrected samples indicating non-normally distributed data. (D) Distribution of the differences between corrected and baseline NSE values, where the corrected group was divided into subgroups based on the H-index.

Figure 3. The diagnostic performance of corrected NSE in case of SCLC.

(A) ROC curves constructed with the us of uncorrected and corrected NSE values and corresponding AUCs (median). (B) QQ-plots of the difference between the AUC of uncorrected and corrected NSE indicating non-normally distributed data.

Figure 4

Optimal cut-off values for SCLC diagnostics of (A) uncorrected and (B) corrected NSE determined by the Youden’s J statistic and stratified bootstrapping. (C) Boxplots of the optimal cut-off values, showing a significant decrease in cut-off value after correction.